m/gemma2:27b-max

m/ gemma2:27b-max

411 Downloads Updated 1 year ago

Gemma2 but with the max context size

ollama run m/gemma2:27b-max

curl http://localhost:11434/api/chat \
  -d '{
    "model": "m/gemma2:27b-max",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='m/gemma2:27b-max',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'm/gemma2:27b-max',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

4f4b5dc2443e · 16GB ·

model

archgemma2

parameters27.2B

quantizationQ4_0

16GB

license

Gemma Terms of Use Last modified: February 21, 2024 By using, reproducing, modifying, distributing,

8.4kB

params

{ "num_ctx": 8192, "stop": [ "<start_of_turn>", "<end_of_turn>" ] }

80B

template

<start_of_turn>user {{ if .System }}{{ .System }} {{ end }}{{ .Prompt }}<end_of_turn> <start_of_turn

136B

Readme

This is simply the regular Gemma 2 model with one exception and that is setting num_ctx to 8192 which is the maximum context size. Source model is https://ollama.com/library/gemma2